Tavily Cursor MCP Server

Instructions

Implementation Reference

• index.js:247-262 (handler)

  Handler for tavily_search_qna tool: calls Tavily search API with include_answer=true and returns the answer or full JSON result.

  case "tavily_search_qna": {
    const result = await tavilyClient.search({
      query: args.query,
      search_depth: args.search_depth || "basic",
      include_answer: true,
    });
  
    return {
      content: [
        {
          type: "text",
          text: result.answer || JSON.stringify(result, null, 2),
        },
      ],
    };
  }

• index.js:153-173 (schema)

  Input schema and metadata for the tavily_search_qna tool, registered in listTools response.

  {
    name: "tavily_search_qna",
    description:
      "Get a direct answer to a question using Tavily's Q&A optimized search. Returns a concise answer to specific questions.",
    inputSchema: {
      type: "object",
      properties: {
        query: {
          type: "string",
          description: "The question to answer",
        },
        search_depth: {
          type: "string",
          enum: ["basic", "advanced"],
          description: "Search depth",
          default: "basic",
        },
      },
      required: ["query"],
    },
  },

• index.js:17-34 (helper)

  TavilyClient.search method: performs the actual API call to Tavily search endpoint, used by tavily_search_qna with include_answer flag.

  async search(params) {
    const response = await fetch(`${this.baseUrl}/search`, {
      method: "POST",
      headers: {
        "Content-Type": "application/json",
      },
      body: JSON.stringify({
        api_key: this.apiKey,
        ...params,
      }),
    });
  
    if (!response.ok) {
      throw new Error(`Tavily API error: ${response.statusText}`);
    }
  
    return await response.json();
  }